Baidu Search
A search server for the Model Context Protocol (MCP) that uses the Baidu Wenxin API.
Baidu Search MCP Server
这是一个用于 Model Context Protocol (MCP) 的百度搜索服务器实现,它允许AI助手使用百度文心API进行智能搜索。
功能特性
- 支持使用百度文心API进行智能搜索
- 支持多种模型选择(ernie-3.5-8k, ernie-4.0-8k, deepseek-r1, deepseek-v3)
- 提供搜索结果和参考来源
- 支持深度搜索和时效性过滤
安装
npm install @modelcontextprotocol/sdk axios
配置
-
首先需要获取百度文心API密钥:
- 访问 百度智能云
- 创建应用并获取API密钥
-
设置环境变量:
export BAIDU_API_KEY=your_api_key_here
使用方法
作为独立服务器运行
node build/index.js
在MCP配置中使用
在你的MCP设置文件中添加以下配置:
{
"mcpServers": {
"baidu-search": {
"command": "node",
"args": ["/path/to/baidu-search-mcp/build/index.js"],
"env": {
"BAIDU_API_KEY": "your_api_key_here"
},
"disabled": false,
"autoApprove": []
}
}
}
API
baidu_search
搜索工具支持以下参数:
query(必需): 搜索查询文本model: 使用的模型名称- 可选值: "ernie-3.5-8k", "ernie-4.0-8k", "deepseek-r1", "deepseek-v3"
- 默认值: "ernie-3.5-8k"
search_mode: 搜索模式- 可选值: "auto", "required", "disabled"
- 默认值: "auto"
enable_deep_search: 是否开启深度搜索(默认:false)search_recency_filter: 搜索结果的时效性范围- 可选值: "week", "month", "semiyear", "year"
开发
- 克隆仓库
- 安装依赖:
npm install
- 编译TypeScript:
npm run build
许可证
MIT License
贡献
欢迎提交 Issues 和 Pull Requests!
免责声明
本项目不对API密钥的使用承担责任,请确保遵守百度文心API的使用条款和政策。
相關伺服器
Obsidian Omnisearch
Search your Obsidian vault using the Omnisearch plugin via a REST API.
YaCy MCP Server
MCP (Model Context Protocol) Server implementation that provides AI tools to search using YaCy web search API.
LeadMagic
Access LeadMagic's B2B data enrichment API suite for email finding, profile enrichment, and company intelligence.
MCP RAG
A managed Retrieval-Augmented Generation (RAG) server using MCP, integrated with knowledge bases and OpenSearch.
Yandex Search
A web search server that uses the Yandex Search API.
gnosis-mcp
Zero-config knowledge base for AI coding agents. Loads your markdown docs into a searchable database and exposes them as MCP tools — search, read, and manage documentation without leaving your editor. Works instantly with SQLite (no setup), upgrades to PostgreSQL + pgvector for hybrid semantic search. Includes skills for searching docs (/gnosis:search), health checks (/gnosis:status), doc management (/gnosis:manage), and first-time setup (/gnosis:setup). 6 MCP tools, 3 resources, FTS5 keyword search, 176 tests.
MCP Open Library
A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.
IP2Location.io
IP2Location.io API integration to retrieve the geolocation information for an IP address.
Kagi
Kagi search API integration
Web Search MCP
Scrapes Google search results using a headless browser. Requires Chrome to be installed.